lyrics 0.0.2

data/lib/lyrics/lyrics_AZLyrics.rb

@@ -0,0 +1,113 @@
+# Copyright (C) 2006-2008 by Sergio Pistone
+# sergio_pistone@yahoo.com.ar
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the
+# Free Software Foundation, Inc.,
+# 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+$LOAD_PATH << File.expand_path(File.dirname(__FILE__))
+
+require "utils/strings"
+require "lyrics"
+
+class AZLyrics < Lyrics
+
+	def AZLyrics.site_host()
+		return "www.azlyrics.com"
+	end
+
+	def AZLyrics.site_name()
+		return "AZ Lyrics"
+	end
+
+	def AZLyrics.lyrics_test_data()
+		return [
+			Request.new( "Radiohead", "Optimistic", "Kid A" ),
+			Request.new( "Pearl Jam", "Alive", "Ten" ),
+			Request.new( "Massive Attack", "Protection", "Protection" ),
+			Request.new( "Portishead", "Wandering Star", "Dummy" ),
+		]
+	end
+
+	def AZLyrics.build_song_add_url( request )
+		return "http://#{site_host()}/add.html"
+	end
+
+	def AZLyrics.build_google_feeling_lucky_url( artist, title=nil )
+		query = Strings.google_search_quote( artist )
+		query << " " << Strings.google_search_quote( title ) if title
+		query << " lyrics"
+		return Strings.build_google_feeling_lucky_url( query, title ? "#{site_host()}/lyrics" : site_host() )
+	end
+
+	def build_lyrics_fetch_data( request )
+		return FetchPageData.new( build_google_feeling_lucky_url( request.artist, request.title ) )
+	end
+
+	def lyrics_page_valid?( request, page_body, page_url )
+		md = /<TITLE>([^<]+) LYRICS - ([^<]+)<\/TITLE>/.match( page_body )
+		return md ?
+			Strings.normalize( request.artist ) == Strings.normalize( md[1] ) &&
+			Strings.normalize( request.title ) == Strings.normalize( md[2] ) :
+			false
+	end
+
+	def parse_lyrics( response, page_body )
+
+		page_body = Strings.latin12utf8( page_body )
+		page_body.tr_s!( " \n\r\t", " " )
+
+		if (md = /<B>([^<]+) LYRICS ?<\/B> ?<BR> ?<BR> ?<FONT size=2> ?<B> ?"([^<]+)" ?<\/b>/.match( page_body ))
+			response.artist, response.title = Strings.titlecase( md[1], true, true ), md[2]
+		end
+
+		return if ! page_body.sub!( /^.*"<\/b><BR> ?<BR> ?/i, "" )
+		return if ! page_body.sub!( /\ ?<BR> ?<BR> ?\[ <a href=.*$/i, "" )
+
+		page_body.gsub!( /<i>\[Thanks to.*$/i, "" )
+		page_body.gsub!( /\ ?<br ?\/?> ?/i, "\n" )
+		page_body.gsub!( /\n{3,}/, "\n\n" )
+
+		response.lyrics = page_body
+	end
+
+	def build_suggestions_fetch_data( request )
+		return FetchPageData.new( build_google_feeling_lucky_url( request.artist ) )
+	end
+
+	def suggestions_page_valid?( request, page_body, page_url )
+		md = /<TITLE>([^<]+) lyrics<\/TITLE>/.match( page_body )
+		return md ? Strings.normalize( request.artist ) == Strings.normalize( md[1] ) : false
+	end
+
+	def parse_suggestions( request, page_body, page_url )
+
+		page_body = Strings.latin12utf8( page_body )
+		page_body.tr_s!( " \n\r\t", " " )
+
+		suggestions = []
+
+		return suggestions if ! page_body.gsub!( /.*<tr><td align=center valign=top> <font face=verdana size=5><br> ?<b>[^<]+ lyrics<\/b>/i, "" )
+		return suggestions if ! page_body.gsub!( /<\/font> ?<\/font> ?<\/td> ?<\/tr> ?<\/table>.*$/i, "" )
+
+		page_body.split( /<br>/i ).each() do |entry|
+			if (md = /<a href="\.\.([^"]+)" target="_blank">([^<]+)<\/a>/i.match( entry ))
+				suggestions << Suggestion.new( request.artist, md[2], "http://#{site_host()}#{md[1]}" )
+			end
+		end
+
+		return suggestions
+	end
+
+end

data/lib/lyrics/lyrics_DarkLyrics.rb

@@ -0,0 +1,124 @@
+# Copyright (C) 2006-2008 by Sergio Pistone
+# sergio_pistone@yahoo.com.ar
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the
+# Free Software Foundation, Inc.,
+# 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+$LOAD_PATH << File.expand_path(File.dirname(__FILE__))
+
+require "utils/strings"
+require "lyrics"
+
+class DarkLyrics < Lyrics
+
+	def DarkLyrics.site_host()
+		return "www.darklyrics.com"
+	end
+
+	def DarkLyrics.site_name()
+		return "Dark Lyrics"
+	end
+
+	def DarkLyrics.lyrics_test_data()
+		return [
+			Request.new( "Opeth", "Hope Leaves", "Damnation" ),
+			Request.new( "Megadeth", "À tout le monde", "Youthanasia" ),
+			Request.new( "Metallica", "Master of Puppets", "Master of Puppets" ),
+			Request.new( "Lacuna Coil", "Heaven's a Lie", "Comalies" ),
+		]
+	end
+
+	def DarkLyrics.build_song_add_url( request )
+		return "http://#{site_host()}/submit.html"
+	end
+
+	def DarkLyrics.build_google_feeling_lucky_url( artist, title=nil )
+		query = Strings.google_search_quote( artist )
+		query << " " << Strings.google_search_quote( title ) if title
+		query << " lyrics"
+		return Strings.build_google_feeling_lucky_url( query, title ? "#{site_host()}/lyrics" : site_host() )
+	end
+
+	def build_lyrics_fetch_data( request )
+		return FetchPageData.new( build_google_feeling_lucky_url( request.artist, request.title ) )
+	end
+
+	def lyrics_page_valid?( request, page_body, page_url )
+		md = /<title>([^<]+) LYRICS - [^<]+<\/title>/.match( page_body )
+		return md ? Strings.normalize( request.artist ) == Strings.normalize( md[1] ) : false
+	end
+
+	def parse_lyrics( response, page_body )
+
+# 		page_body = Strings.latin12utf8( page_body )
+		page_body.tr_s!( " \n\r\t", " " )
+
+		if (md = /<FONT size=5 color=#FFFFCC>([^<]+) LYRICS<\/FONT><br>/.match( page_body ))
+			response.artist = Strings.titlecase( md[1], true, true )
+		end
+
+		if (md = /<FONT size=3 color=white><b>([^<]+) \(([0-9]{4,4})( [^\)]+|)\)<\/b><\/FONT><br>/.match( page_body ))
+			response.album, response.year = md[1], md[2]
+		end
+
+		return if ! page_body.sub!( /^.*<SCRIPT LANGUAGE="javascript" src="\.\.\/\.\.\/recban\.js"><\/SCRIPT><BR>/i, "" )
+		return if ! page_body.sub!( /<FONT [^>]*size=.*$/i, "" )
+
+		md = /.*#([0-9]+)$/.match( response.url )
+		track = md ? md[1] : nil
+		normalized_title = Strings.normalize( response.request.title )
+		page_body.split( /<a name=[0-9]+><FONT color=#DDDDDD>/i ).each() do |song_content|
+			md = /^<b>([0-9]+)\. ([^<]+)<\/b><\/font><br>(.*)$/.match( song_content )
+			next if ! md || (track && track != md[1]) || (! track && normalized_title != Strings.normalize( md[2] ))
+			response.title = md[2]
+			page_body = md[3]
+			page_body.gsub!( /\ ?<br ?\/?> ?/i, "\n" )
+			page_body.gsub!( /\n{3,}/, "\n\n" )
+			page_body.strip!()
+			response.lyrics = page_body
+		end
+
+	end
+
+	def build_suggestions_fetch_data( request )
+		return FetchPageData.new( build_google_feeling_lucky_url( request.artist ) )
+	end
+
+	def suggestions_page_valid?( request, page_body, page_url )
+		md = /<title>([^<]+) LYRICS<\/title>/.match( page_body )
+		return md ? Strings.normalize( request.artist ) == Strings.normalize( md[1] ) : false
+	end
+
+	def parse_suggestions( request, page_body, page_url )
+
+# 		page_body = Strings.latin12utf8( page_body )
+		page_body.tr_s!( " \n\r\t", " " )
+
+		suggestions = []
+
+		return suggestions if ! page_body.sub!(/^.*<FONT FACE="Helvetica" COLOR=#FFFFCC SIZE=4><br>[^<]+ LYRICS<BR><\/FONT>/i,"")
+		return suggestions if ! page_body.sub!( /<SCRIPT LANGUAGE="javascript".*$/i, "" )
+
+		page_body.split( /<br>/i ).each() do |entry|
+			if (md = /<a href="\.\.(\/lyrics\/[^"]+)" target="_blank"><FONT [^>]+>([^"]+)<\/FONT><\/a>/i.match( entry ))
+				suggestions << Suggestion.new( request.artist, md[2], "http://#{site_host()}#{md[1]}" )
+			end
+		end
+
+		return suggestions
+
+	end
+
+end

data/lib/lyrics/lyrics_Giitaayan.rb

@@ -0,0 +1,124 @@
+# Copyright (C) 2007-2008 by
+# Swapan Sarkar <swapan@yahoo.com>
+# Sergio Pistone <sergio_pistone@yahoo.com.ar>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the
+# Free Software Foundation, Inc.,
+# 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+$LOAD_PATH << File.expand_path(File.dirname(__FILE__))
+
+require "utils/strings"
+require "utils/itrans"
+require "lyrics"
+
+require "cgi"
+
+class Giitaayan < Lyrics
+
+# 	@@prefix = "http://s94437128.onlinehome.us/isb/cisb/"
+# 	@@prefix = "http://gaane.giitaayan.com/cisb/"
+	@@prefix = "http://thaxi.hsc.usc.edu/rmim/giitaayan/cisb/"
+	@@prefix_regexp = /<a href=" *(#{@@prefix.gsub( "\\", "\\\\" ).gsub( ".", "\\." )}[^"]+.isb)">/
+
+	def Giitaayan.site_host()
+		return "www.giitaayan.com"
+	end
+
+	def Giitaayan.site_name()
+		return "Giitaayan"
+	end
+
+	def Giitaayan.lyrics_test_data()
+		return [
+			Request.new( "Abhijit, Kavita Subramaniam", ITRANS.to_devanagari( "a.ndherii raat me.n ham aur tum" ), "Juhi" ),
+			Request.new( "Poornima, Chorus", ITRANS.to_devanagari( "a aa ii u u uu meraa dil na to.Do" ), "Raajaa Baabu" ),
+			Request.new( "Sonu Nigam, Chorus", ITRANS.to_devanagari("gayaa gayaa dil jaane de" ), "Fizaa" ),
+			Request.new( "Lata, Hemant", ITRANS.to_devanagari( "ulajh gaye do nainaa, dekho" ), "Ek Saal" ),
+		]
+	end
+
+	def Giitaayan.known_url?( url )
+		return url.index( @@prefix ) == 0
+	end
+
+	def Giitaayan.build_song_add_url( request )
+		return "http://#{site_host()}/submit.asp"
+	end
+
+	def parse_lyrics( response, page_body )
+
+		custom_data = {}
+
+		["stitle", "film", "year", "starring", "singer", "music", "lyrics"].each() do |key|
+			if (md = /\\#{key}\{(.+)\}%/.match( page_body ))
+				custom_data[key] = md[1]
+			end
+		end
+
+		response.artist = custom_data["singer"]
+		response.album = custom_data["film"]
+		response.year = custom_data["year"]
+
+		custom_data["lyricist"] = custom_data["lyrics"] if ! Strings.empty?( custom_data["lyrics"] )
+		if ! Strings.empty?( custom_data["music"] ) || ! Strings.empty?( custom_data["lyrics"] )
+			custom_data["credits"] = "#{custom_data["music"]} #{custom_data["lyrics"]}".strip()
+		end
+		if ! Strings.empty?( custom_data["stitle"] )
+			custom_data["stitle"] = ITRANS.to_devanagari( custom_data["stitle"] )
+			response.title = custom_data["stitle"]
+		end
+
+		response.custom_data = custom_data
+
+		return if ! page_body.gsub!( /^.*\n#indian\s*\n%?/m, "" )
+		return if ! page_body.gsub!( /%?\s*\n#endindian.*$/m, "" )
+
+		page_body.gsub!( "\\threedots", "..." )
+		page_body.gsub!( "\\-", "-" )
+		page_body.gsub!( "\\:", ":" )
+		page_body.gsub!( /%[^\n]*/, "" )
+
+		response.lyrics = ITRANS.to_devanagari( page_body )
+
+	end
+
+	def build_suggestions_fetch_data( request )
+		title = CGI.escape( ITRANS.from_devanagari( request.title ) )
+		return FetchPageData.new( "http://#{site_host()}/search.asp?browse=stitle&s=#{title}" )
+	end
+
+	def parse_suggestions( request, page_body, page_url )
+
+		page_body.tr_s!( " \n\r\t", " " )
+
+		suggestions = []
+
+		return suggestions if page_body.include?( "Sorry, no song found for your search!" )
+		return suggestions if ! page_body.sub!( /^.*<div align="center"><b>Lyrics<\/b><\/div> ?<\/td> ?<\/tr> ?<tr>/, "" )
+		return suggestions if ! page_body.sub!( /<form name="form1" method="get" action="search\.asp".*$/, "" )
+
+		page_body.gsub!( /<br> ?Page <b>1<\/b> ?<a href="search.asp\?PageNo=2&s=na&browse=stitle">.*$/, "" )
+
+		page_body.split( /<\/tr> ?<tr> ?/ ).each() do |sugg|
+			if (md1 = /^ ?<td>([^<]+) - <a/.match( sugg )) && (md2 = @@prefix_regexp.match( sugg ))
+				suggestions << Suggestion.new( request.artist, ITRANS.to_devanagari( md1[1] ), md2[1] )
+			end
+		end
+
+		return suggestions
+
+	end
+
+end

data/lib/lyrics/lyrics_Jamendo.rb

@@ -0,0 +1,166 @@
+# Copyright (C) 2006-2008 by
+# Eduardo Robles Elvira <edulix@gmail.com>
+# Sergio Pistone <sergio_pistone@yahoo.com.ar>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the
+# Free Software Foundation, Inc.,
+# 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+$LOAD_PATH << File.expand_path(File.dirname(__FILE__))
+
+require "utils/strings"
+require "utils/http"
+require "lyrics"
+
+class Jamendo < Lyrics
+
+	def Jamendo.site_host()
+		return "www.jamendo.com"
+	end
+
+	def Jamendo.site_name()
+		return "Jamendo"
+	end
+
+	def Jamendo.lyrics_test_data()
+		return [
+			Request.new( "Misantropía", "Hipócrita (Hypocrite)", "Misantropía" ),
+			Request.new( "Inesperado", "Pez Gordo", "Maqueta Inesperada" ),
+			Request.new( "Black Venus", "Vents de Mars", "Immortel" ),
+			Request.new( "Punkamine", "Gora gerra", "Punkamine" ),
+		]
+	end
+
+	def Jamendo.cleanup_artist_name( artist )
+		artist = Strings.downcase( artist )
+		Strings.remove_vocal_accents!( artist )
+		artist.gsub!( /\[|\]|:/, "" )
+		artist.gsub!( /_| |'|"|ø|&|@|\/|\*|\.|®|%|#/, " " ) # \' can also be ''
+		artist.squeeze!( " " )
+		artist.strip!()
+		artist.gsub!( " ", "." )
+		return artist
+	end
+
+	def cleanup_artist_name( artist )
+		self.class.cleanup_artist_name( artist )
+	end
+
+	def build_lyrics_fetch_data( request )
+		url =  "http://#{site_host()}/en/get/track/list/track-artist-album/lyricstext/plain/?"
+		url << "searchterm=#{CGI.escape( request.title )}"
+		url << "&artist_searchterm=#{CGI.escape( request.artist )}"
+		url << "&album_searchterm=#{CGI.escape( request.album )}" if request.album
+		return FetchPageData.new( url )
+	end
+
+	def suggestions_page_valid?( request, page_body, page_url )
+		return	page_url.index( "http://#{site_host()}/en/artist/" ) ||
+				page_url.index( "http://#{site_host()}/en/album/" )
+	end
+
+	def parse_lyrics( response, page_body )
+
+		if /track-artist-album/.match( response.url )
+
+			page_body.tr_s!( " \r\t", " " )
+
+			md = /[?&]searchterm=([^&]+)(&?|$)/.match( response.url )
+			response.title = CGI.unescape( md[1] ) if md
+
+			md = /[?&]artist_searchterm=([^&]+)(&?|$)/.match( response.url )
+			response.artist = CGI.unescape( md[1] ) if md
+
+			md = /[?&]album_searchterm=([^&]+)(&?|$)/.match( response.url )
+			response.album = CGI.unescape( md[1] ) if md
+
+			response.lyrics = page_body if ! page_body.empty?
+
+		else
+
+			page_body.tr_s!( " \n\r\t", " " )
+
+			if (md = /<h1>([^<]+)<\/h1><p> by <a href="\/en\/artist\/[^"]+"[^<]*>([^<]+)<\/a>/.match( page_body ))
+				response.title = md[1].strip()
+				response.artist = md[2].strip()
+			end
+
+			if (md = /<a class="i l a" href="http:\/\/#{site_host()}\/en\/album\/[^"]+" ?>([^<]+)<\/a>/.match( page_body ))
+				response.album = md[1].strip()
+			end
+
+			custom_data = {}
+			["release", "genre"].each() do |key|
+				md = /<tr class='[a|b]'> ?<td class='l'>#{key}<\/td> ?<td class='[^']+'>([^<]+)<\/td> ?<\/tr>/i.match( page_body )
+				custom_data[key] = md[1].strip() if md
+			end
+
+			response.custom_data = custom_data
+			response.year = custom_data["release"].gsub( /.*,/, "" ) if custom_data.include?( "release" )
+
+			return if ! page_body.sub!( /^.*<div id="lyrics"[^>]*>/, "" )
+			return if ! page_body.sub!( /<\/div>.*$/, "" )
+
+			page_body.gsub!( /\ ?<br ?\/?> ?/i, "\n" )
+
+			response.lyrics = page_body
+
+		end
+
+	end
+
+	def build_suggestions_fetch_data( request )
+		return FetchPageData.new(
+			Strings.build_google_feeling_lucky_url(
+				"artist " + Strings.google_search_quote( "albums of #{request.artist}" ),
+				"#{site_host()}/en"
+			)
+		)
+	end
+
+	def parse_suggestions( request, page_body, page_url )
+
+		page_body.tr_s!( " \n\r\t", " " )
+
+		suggestions = []
+
+		if page_url.index( "http://#{site_host()}/en/artist/" )
+
+			return suggestions if ! page_body.sub!( /^.*<h2 class="seo_message" ?>Albums of [^<]+<\/h2>/, "" )
+			return suggestions if ! page_body.sub!( /<h3>More information...<\/h3>.*$/, "" )
+
+			page_body.split( /<h2 class='g_album_name'>/ ).each() do |album_entry|
+				if (md = /<a title="[^"]+" href="(\/en\/album\/[0-9]+)" >([^<]+)<\/a>/.match( album_entry ))
+					suggestions << FetchPageData.new( "http://#{site_host()}#{md[1]}" )
+				end
+			end
+
+		elsif page_url.index( "http://#{site_host()}/en/album/" )
+
+			return suggestions if ! page_body.sub!( /^.*<tbody>/, "" )
+			return suggestions if ! page_body.sub!( /<\/tbody>.*$/, "" )
+
+			page_body.split( "<td class=\"title_tracks\">" ).each() do |song_entry|
+				if (md = /<a href="(\/en\/track\/[0-9]+)" title="[^"]*" ?>([^<]+)<\/a>/.match( song_entry ))
+					suggestions << Suggestion.new( request.artist, md[2].strip(), "http://#{site_host()}#{md[1]}" )
+				end
+			end
+
+		end
+
+		return suggestions
+
+	end
+
+end